首页|University of Turku Reports Findings in Gliomas (Raman-based machine learning pl atform reveals unique metabolic differences between IDHmut and IDHwt glioma)
University of Turku Reports Findings in Gliomas (Raman-based machine learning pl atform reveals unique metabolic differences between IDHmut and IDHwt glioma)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-New research on Oncology - Gliomas is the subject of a report. According to news reporting out of Turku, Finland, by N ewsRx editors, research stated, "Formalin-fixed, paraffin-embedded (FFPE) tissue slides are routinely used in cancer diagnosis, clinical decision-making, and st ored in biobanks, but their utilization in Raman spectroscopy-based studies has been limited due to the background coming from embedding media. Spontaneous Rama n spectroscopy was used for molecular fingerprinting of FFPE tissue from 46 pati ent samples with known methylation subtypes." Our news journalists obtained a quote from the research from the University of T urku, "Spectra were used to construct tumor/non-tumor, IDH1WT/IDH1mut, and methy lation-subtype classifiers. Support vector machine and random forest were used t o identify the most discriminatory Raman frequencies. Stimulated Raman spectrosc opy was used to validate the frequencies identified. Mass spectrometry of glioma cell lines and TCGA were used to validate the biological findings. Here we deve lop APOLLO (rAmanbased PathOLogy of maLignant glioma) - a computational workflo w that predicts different subtypes of glioma from spontaneous Raman spectra of F FPE tissue slides. Our novel APOLLO platform distinguishes tumors from nontumor tissue and identifies novel Raman peaks corresponding to DNA and proteins that a re more intense in the tumor. APOLLO differentiates isocitrate dehydrogenase 1 m utant (IDH1mut) from wildtype (IDH1WT) tumors and identifies cholesterol ester l evels to be highly abundant in IDHmut glioma. Moreover, APOLLO achieves high dis criminative power between finer, clinically relevant glioma methylation subtypes , distinguishing between the CpG island hypermethylated phenotype (G-CIMP)-high and G-CIMP-low molecular phenotypes within the IDH1mut types."
TurkuFinlandEuropeCyborgsEmergin g TechnologiesGliomasHealth and MedicineMachine LearningOncology
NETL
NSTL
